customer-health-analyst

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists entirely of Markdown documentation providing frameworks and guidance for customer success metrics. No Python, JavaScript, shell scripts, or binary files are included in the package.
  • [Indirect Prompt Injection] (LOW): The skill identifies external data sources as inputs for health scoring, which represents a theoretical ingestion surface.
  • Ingestion points: 'rules/health-score-design.md' suggests the analysis of 'AI-analyzed support conversations,' 'Ticket sentiment,' 'Call transcripts,' and 'CSM notes.'
  • Boundary markers: None provided in the methodology.
  • Capability inventory: The skill itself contains no code and thus lacks the system-level capabilities (e.g., file writing, network access) required to exploit this surface.
  • Sanitization: No sanitization or escaping techniques are discussed for the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:24 PM